Automated Prediction of Diabetes Mellitus using Infrared Thermal Foot Images: Recurrent Neural Network Approach

Millions of people worldwide are affected by Diabetes Mellitus (DM), which is a chronic disease. Evaluation of the DM indicator, namely blood glucose level, requires invasive methods such as glucometer or blood tests, which cause discomfort to the patient. Automated noninvasive monitoring methods are urgently needed to ensure consistency and better treatment. The regular monitoring of DM can prevent or delay the onset of complications. Thermal foot images have been proposed as noninvasive methods for the prediction of DM. Thermograms were acquired at Mittal Eye Hospital, Sangrur, India, from 50 participants in the diabetic (without neuropathic conditions) and non-diabetic groups using a thermal camera (FLIR E-60). This study proposes an automated prediction system for DM using thermal foot images and Recurrent Neural Network (RNN) approach. The proposed system processes the thermal images and extracts relevant features using a CNN (Convolutional Neural Network). The extracted features were then fed to the RNN to predict the presence or absence of the DM. The experimental results demonstrate that the proposed framework attains an accuracy of (97.14 ± 1.5) %, surpassing the predictive capabilities of light-weight convolutional neural network (Lw-CNN), which only achieves an accuracy of (82.9 ± 3) % in predicting DM. This performance outperformed other state-of-the-art methods in the field. Our approach has the potential to be used as prediction tool for DM. Therefore, the proposed system has the potential for prediction of DM and improve patient outcomes by enabling timely intervention. Future work should focus on evaluating the proposed system on a larger dataset and integrating it with clinical decision support systems for personalized care. This study holds the promise of transforming DM screening and diagnosis, leading to enhanced patient outcomes.

Pharmaceutical applications of a nanospectroscopic technique: Surface-enhanced Raman spectroscopy

Surface-enhanced Raman spectroscopy (SERS) is a very sensitive technique offering unique opportunities for detection and identification of molecules and molecular structures at extremely low concentrations even in complex sample matrixes. Since a nanostructured noble metal surface is required for the enhancement of Raman scattering, the acquired spectral information naturally originates from nanometer size domains making it a nanospectroscopic technique by breaking the diffraction limit of light. In this review, first Raman spectroscopy, its comparison to other related techniques, its modes and instrumentation are briefly introduced. Then, the SERS mechanism, substrates and the parameters influencing a SERS experiment are discussed. Finally, its applications in pharmaceuticals including drug discovery, drug metabolism, multifunctional chemo-photothermal-therapy-delivery-release-imaging, drug stability and drug/metabolite detection in complex biological samples are summarized and elaborated.

A CMOS Front-End Interface ASIC for SiPM-based Positron Emission Tomography Imaging Systems

A current-mode interface chip for Silicon Photomultiplier (SiPM) array based positron emission tomography (PET) imaging front-ends is described. The circuit uses a high-speed current amplifier with a low input impedance, to minimize signal loss at the SiPM amplifier interface. To reduce the impact of dark noise, a novel high-speed threshold detection/comparator circuit is used to remove unwanted noise events. A prototype chip interfaces an array of SiPMs to the digital backend of a Positron Emission Tomography (PET) system using 64 readout channels, each of which contain a current amplifier and a threshold detection component. To reduce the number of backend channels, a row-column pulse positioning architecture (RCA) has been implemented. The ASIC occupies an area of 14.04 mm² in 130nm STMicroelectronics HCMOS9GP process. The measured input impedance of the current amplifier is 20 ohms at 10 MHz, while the threshold detection circuit's propagation delay is 0.3-2ns.

Multi-photon vertical cross-sectional imaging with a dynamically-balanced thin-film PZT z-axis microactuator

Use of a thin-film piezoelectric microactuator for axial scanning during multi-photon vertical cross-sectional imaging is described. The actuator uses thin-film lead-zirconate-titanate (PZT) to generate upward displacement of a central mirror platform, micro-machined from a silicon-on-insulator (SOI) wafer to dimensions compatible with endoscopic imaging instruments. Device modeling in this paper focuses on existence of frequencies near device resonance producing vertical motion with minimal off-axis tilt even in the presence of multiple vibration modes and non-uniformity in fabrication outcomes. Operation near rear resonance permits large stroke lengths at low voltages relative to other vertical microactuators. Highly uniform vertical motion of the mirror platform is a key requirement for vertical cross-sectional imaging in the remote scan architecture being used for multi-photon instrument prototyping. The stage is installed in a benchtop testbed in combination with an electrostatic mirror that performs in-plane scanning. Vertical sectional images are acquired from 15 μm diameter beads and excised mouse colon tissue.

Mechanically Tunable Hollow Silica Ultrathin Nanoshells for Ultrasound Contrast Agents

Perfluoropentane (PFP) gas filled biodegradable iron-doped silica nanoshells have been demonstrated as long-lived ultrasound contrast agents. Nanoshells are synthesized by a sol-gel process with tetramethyl orthosilicate (TMOS) and iron ethoxide. Substituting a fraction of the TMOS with R-substituted trialkoxysilanes produces ultrathin nanoshells with varying shell thicknesses and morphologies composed of fused nanoflakes. The ultrathin nanoshells had continuous ultrasound Doppler imaging lifetimes exceeding 3 hours, were twice as bright using contrast specific imaging, and had decreased pressure thresholds compared to control nanoshells synthesized with just TMOS. Transmission electron microscopy (TEM) showed that the R-group substituted trialkoxysilanes could reduce the mechanically critical nanoshell layer to 1.4 nm. These ultrathin nanoshells have the mechanical behavior of weakly linked nanoflakes but the chemical stability of silica. The synthesis can be adapted for general fabrication of three-dimensional nanostructures composed of nanoflakes, which have thicknesses from 1.4-3.8 nm and diameters from 2-23 nm.

Closed loop adaptive optics for microscopy without a wavefront sensor

A three-dimensional wide-field image of a small fluorescent bead contains more than enough information to accurately calculate the wavefront in the microscope objective back pupil plane using the phase retrieval technique. The phase-retrieved wavefront can then be used to set a deformable mirror to correct the point-spread function (PSF) of the microscope without the use of a wavefront sensor. This technique will be useful for aligning the deformable mirror in a widefield microscope with adaptive optics and could potentially be used to correct aberrations in samples where small fluorescent beads or other point sources are used as reference beacons. Another advantage is the high resolution of the retrieved wavefont as compared with current Shack-Hartmann wavefront sensors. Here we demonstrate effective correction of the PSF in 3 iterations. Starting from a severely aberrated system, we achieve a Strehl ratio of 0.78 and a greater than 10-fold increase in maximum intensity.

EXPLORING FUNCTIONAL CONNECTIVITY IN FMRI VIA CLUSTERING

In this paper we investigate the use of data driven clustering methods for functional connectivity analysis in fMRI. In particular, we consider the K-Means and Spectral Clustering algorithms as alternatives to the commonly used Seed-Based Analysis. To enable clustering of the entire brain volume, we use the Nyström Method to approximate the necessary spectral decompositions. We apply K-Means, Spectral Clustering and Seed-Based Analysis to resting-state fMRI data collected from 45 healthy young adults. Without placing any a priori constraints, both clustering methods yield partitions that are associated with brain systems previously identified via Seed-Based Analysis. Our empirical results suggest that clustering provides a valuable tool for functional connectivity analysis.